Is the Avoid Feature Creep skill free?

Yes. The skill itself is free from waynesutton/convexskills. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Avoid Feature Creep SkillProof Score?

8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 4/5.

How do I install Avoid Feature Creep?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Avoid Feature Creep with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Avoid Feature Creep

Gates feature requests through an evidence checklist before they enter scope

by waynesutton · waynesutton/convexskills

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.4/10
Tested: Aug 5, 2026
Environment: Claude Code 2.x (agent harness)

⚠ This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (repo unreachable/deleted). The test below is what we measured on Aug 5, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.

Ran the same three-weeks-to-launch scope question with and without it: the unguided answer waved dark mode through purely because it was cheap, while the skill's gate ('no YES to questions 1-3 with evidence, do not build') rejected all three and forced the counter-offer 'which of search, offline sync or export do we cut to make room?'. It also left behind two reusable artifacts the baseline never produced — a SCOPE.md with explicit out-of-scope conditions and a decision log where every row names a trade-off. The cost is length: 574 words against the baseline's 172 for the same three decisions.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 7/10
Docs & honesty 4/5

What Avoid Feature Creep does

A scope-discipline framework that runs feature requests through a five-stage checklist (validated problem, vision alignment, measurable impact, complexity, gut check) and produces an MVP scope document plus a scope decision log. Triggers when planning features, reviewing scope, cutting an MVP, cleaning a backlog, or when someone asks for just one more thing. Includes rules for treating AI coding agents as scope-creeping stakeholders.

How to install Avoid Feature Creep

Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.

Commands — how to trigger Avoid Feature Creep

/avoid-feature-creep Gates feature requests through an evidence checklist before they enter scope

It also activates on plain-language prompts like these:

The CEO wants three more features before launch, should we build them?
Help me define the MVP scope for this note-taking app
Our backlog has 200 items and we haven't shipped in four months

Frequently asked questions

Is the Avoid Feature Creep skill free?: Yes. The skill itself is free from waynesutton/convexskills. SkillProof publishes the install command and an independent test verdict at no cost.
Does Avoid Feature Creep work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Aug 5, 2026. Verdict: Tested · Works. Ran the same three-weeks-to-launch scope question with and without it: the unguided answer waved dark mode through purely because it was cheap, while the skill's gate ('no YES to questions 1-3 with evidence, do not build') rejected all three and forced the counter-offer 'which of search, offline sync or export do we cut to make room?'. It also left behind two reusable artifacts the baseline never produced — a SCOPE.md with explicit out-of-scope conditions and a decision log where every row names a trade-off. The cost is length: 574 words against the baseline's 172 for the same three decisions.
What is the Avoid Feature Creep SkillProof Score?: 8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 4/5.
How do I install Avoid Feature Creep?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Avoid Feature Creep with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.